© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48871
    Prev
    Next
    INDEX
    Explanations

    copyrightfunctionmatcheither version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seguida
    -0.74
    Overwatch
    -0.69
    シャワー
    -0.66
    Fatty
    -0.64
     Fatty
    -0.64
    Peg
    -0.63
    Thick
    -0.63
    igreja
    -0.63
     ammi
    -0.62
     tẩy
    -0.60
    POSITIVE LOGITS
    arif
    0.73
    OptionsMenu
    0.73
    Cam
    0.72
    Matcher
    0.71
    menes
    0.71
    MATCH
    0.70
    Match
    0.69
    <0x9C>
    0.68
    MEM
    0.68
     Học
    0.68
    Activations Density 0.111%

    No Known Activations